空间科学学报2025，Vol.45Issue(6)：1460-1470,11.DOI:10.11728/cjss2025.06.2024-0179
基于SegRNN的热层大气密度经验模型校准
Calibration of Thermospheric Atmospheric Density Empirical Model Based on SegRNN
摘要
Abstract
Atmospheric drag is the largest non-gravitational perturbation experienced by low-orbit satellites,and the main source of error in calculating atmospheric drag stems from inaccuracies in the empirical models of thermospheric density.Currently,these empirical models generally exhibit errors ex-ceeding 30%.To enhance the prediction accuracy of these models,a calibration method for thermospher-ic density empirical models based on Segment Recurrent Neural Network(SegRNN)is proposed.This method employs the segmentation and parallelism strategies of SegRNN for model training and inference,mitigating the issues of error accumulation and gradient instability that arise from excessive iterations in traditional RNN.By analyzing the relationship between atmospheric density and external environmen-tal parameters such as Ap,F10.7,and F10.7a,an improved neural network architecture named SegRNN with Residual Block is proposed.This architecture introduces external environmental parameters as dy-namic covariates and employs a residual block to encode these covariates,thereby extracting density-re-lated information for the prediction period and further enhancing the prediction accuracy of SegRNN.Fi-nally,the density data derived from the onboard accelerometer of the GRACE(Gravity Recovery and Climate Experiment)satellite is used to calibrate the NRLMSIS 2.0 model.The results indicate that the original error of the NRLMSIS 2.0 model is 31.3%.After calibration with SegRNN,the error was re-duced to 8.0%.By introducing dynamic covariates,the model error was further reduced to 7.2%.Ulti-mately,the error of the final calibrated model decreased by 24.1%,demonstrating significant calibration effects.关键词
大气密度/经验密度模型/神经网络/模型校准/GRACE加速度计数据Key words
Atmospheric density/Empirical density model/Neural network/Model calibration/GRACE accelerometer data分类
天文与地球科学引用本文复制引用
CAO Qingpeng,HUANG Liupeng,WEI Chunbo,GU Defeng..基于SegRNN的热层大气密度经验模型校准[J].空间科学学报,2025,45(6):1460-1470,11.基金项目
中山大学中央高校基本科研业务费专项资金项目资助 （）
